Fundus data determination method

Abstract

The application relates to the technical field of eye detection, in particular to an eye fundus data determination method. The method comprises the following steps: performing layered processing on first scanning data containing an optic nerve head, determining recognizable layers and an internal limiting membrane, determining a disc edge of the optic nerve head based on the recognizable layers, determining a target curve when a surface area formed by a closed curve extending from the disc edge to the internal limiting membrane meets a preset condition based on the surface area, determining a cup edge of the optic nerve head based on the target curve, and determining eye fundus data according to the disc edge and the cup edge. The method can improve accuracy.

Description

Technical Field

[0001] This application relates to the field of ocular detection technology, and in particular to a method for determining fundus data. Background Technology

[0002] The optic nerve head (ONH), also known as the optic disc, is the area on the retina where optic nerve fibers and retinal blood vessels converge and exit the eyeball. A physiological depression, called the optic cup, usually appears at the center of the optic disc.

[0003] Obtaining fundus data related to ONH (such as optic disc area, optic cup area, cup-to-disc ratio, and optic cup volume) is crucial for the diagnosis and treatment of optic nerve-related diseases. However, obtaining this fundus data depends on the accurate localization of the optic disc margin and optic cup margin.

[0004] However, the accuracy of the fundus data currently available is not high. Summary of the Invention

[0005] Therefore, it is necessary to provide a method for determining fundus data that can improve accuracy in addressing the aforementioned technical problems.

[0006] In a first aspect, this application provides a method for determining fundus data, including:

[0007] The internal limiting membrane and optic disc margins were determined based on the first scan data including the optic nerve head.

[0008] Based on the surface area formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane, the closed curve that satisfies the preset conditions is determined as the target curve;

[0009] The edge of the optic cup of the optic nerve head is determined based on the target curve;

[0010] Fundus data are determined based on the optic disc margin and optic cup margin.

[0011] Secondly, this application also provides a fundus data determination device, comprising:

[0012] The first determining module is used to determine the internal limiting membrane and the edge of the optic disc based on the first scan data including the optic nerve head.

[0013] The second determining module is used to determine the target curve when the surface area meets the preset conditions based on the surface area formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane.

[0014] The third determining module is used to determine the edge of the optic cup of the optic nerve head based on the target curve.

[0015] The fourth determination module is used to determine fundus data based on the optic disc edge and optic cup edge.

[0016] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described fundus data determination method.

[0017] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described fundus data determination method.

[0018] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described fundus data determination method.

[0019] The aforementioned method for determining fundus data, by identifying the internal limiting membrane and optic disc margin based on first scan data including the optic nerve head, and by determining the target curve based on the surface area formed by the closed curve extending from the optic disc margin to the internal limiting membrane, satisfies preset conditions. Therefore, by using the surface area, the surface formed by the closed curve extending from the optic disc margin to the internal limiting membrane can be calculated as a whole. This not only reflects the total number of optic nerves but also yields a highly continuous closed curve. Furthermore, based on the target curve, the optic cup margin of the optic nerve head can be determined relatively accurately, thus enabling the determination of more accurate fundus data based on the optic disc margin and the optic cup margin. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the optic nerve head;

[0022] Figure 2 This is a schematic diagram of OCT technology imaging.

[0023] Figure 3 A schematic diagram of the structure of a healthy human eye;

[0024] Figure 4An OCT image of a nearsighted person's eye;

[0025] Figure 5 A schematic diagram of a fundus image captured by a fundus camera;

[0026] Figure 6 This is an application environment diagram of a fundus data determination method in one embodiment;

[0027] Figure 7 This is a flowchart illustrating a method for determining fundus data in one embodiment;

[0028] Figure 8 This is a schematic diagram of the layering result in one embodiment;

[0029] Figure 9 This is a schematic diagram of the edge of the viewing disk and the edge of the viewing cup in one embodiment;

[0030] Figure 10 This is a schematic diagram of a triangle segmentation process in one embodiment;

[0031] Figure 11 This is a schematic diagram of a process for determining a target curve in one embodiment;

[0032] Figure 12 This is a schematic diagram of a polar coordinate system in one embodiment;

[0033] Figure 13 This is a schematic diagram of another process for determining a target curve in one embodiment;

[0034] Figure 14 This is a flowchart illustrating the process of determining the edge of the viewing disk in one embodiment;

[0035] Figure 15 This is a schematic diagram of a two-dimensional projection image and a first curve in one embodiment;

[0036] Figure 16 This is a schematic diagram showing fundus data in one embodiment;

[0037] Figure 17 This is a schematic diagram of a method for determining fundus data in one embodiment;

[0038] Figure 18 A comparison diagram showing the effects of related technologies and this application;

[0039] Figure 19 This is a structural block diagram of a fundus data determination device in one embodiment. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0041] Figure 1 This is a schematic diagram of the optic nerve head. Figure 1 This illustrates a fundus image acquired using a fundus camera, showing the location of the optic nerve head as follows: Figure 1 As shown by the white circle in the image.

[0042] Optical coherence tomography (OCT) is a technique that uses low-coherence light sources and interference principles to perform high-resolution tomographic imaging of biological tissues. Its applications are particularly widespread in ophthalmology, allowing for non-invasive and rapid scanning and measurement of various physiological structures in the anterior and posterior segments of the eye. In posterior segment applications of OCT, the details of each layer of the retina can be clearly observed through OCT images.

[0043] Figure 2 This is a schematic diagram of OCT imaging technology. Figure 2 Figure (a) shows OCT volumetric data acquired near the ONH location. Figure 2 Figure (b) shows a single frame of tomographic image (B-scan) passing through the center of the ONH. For example... Figure 2 As shown, OCT technology can clearly visualize the optic cup with a central depression in the ONH. Compared to fundus camera images for measuring ONH, the high-resolution data acquired by OCT technology provides a more accurate and refined data foundation.

[0044] The following describes the process of determining the position of the viewing disc in related technologies.

[0045] Figure 3 This is a schematic diagram of the structure of a healthy human eye. Figure 3 This diagram illustrates the relative relationship between the optic cup margin and the nerve fiber layer of the retina in the eye of a healthy person. Figure 3 As shown, the optic disc margin can be referenced by the opening of Bruch's membrane (BM) near the ONH (often referred to as the Bruch's membrane opening, BMO). In other words, in the eyes of a healthy person, the intersection of the Bruch's membrane and the optic nerve fiber layer can well represent the location of the optic disc. Therefore, some related techniques perform layered calculations of the retina when determining the optic disc margin to obtain the location of the BMO and directly define the BMO as the location of the optic disc.

[0046] However, it is not appropriate to define the position of the display screen directly as the position of the BMO in all cases. Figure 4 This is an OCT image of a nearsighted person's eye. Figure 4 401 indicates the end of the brucellosis membrane, which is the location of the BMO, and 402 indicates the junction of the sclera and the optic nerve. For example... Figure 4 As shown, parapapillary atrophy exists in the eyes of some patients with high myopia. This means that the retina, Brucella membrane, and even the underlying choroid atrophy outwards from the point of contact with the optic nerve, exposing the underlying sclera. Furthermore, parapapillary atrophy and the health of the optic nerve are not directly correlated. Therefore, using the BMO (Browser Occlusion Mode) to define the optic disc margin in this case cannot accurately characterize the optic disc size; using the termination position of the sclera is more accurate.

[0047] Besides the methods mentioned above, some related technologies use traditional or deep learning methods to segment fundus images captured by fundus cameras to determine the optic disc position. However, this method is not very accurate.

[0048] Figure 5 A schematic diagram of a fundus image captured by a fundus camera. Figure 5 501 in the text indicates a video disc. Figure 5 502 in the text indicates peripapillary atrophy (PPA), such as... Figure 5 As shown, for human eyes with paradiscal atrophy, the contrast of the atrophied retinal edge and the underlying tissue is usually significantly higher than that of the scleral edge and ONH. Therefore, even if the labeled data used to train the model is correctly labeled, the model can still easily mistake the retinal edge for the optic disc edge when making predictions, thus overestimating the size of the optic disc.

[0049] The following describes the process for determining the optic cup position in related technologies. The optic cup margin is a closed curve located on the upper surface of the inner limiting membrane (ILM). Because the ILM is very thin, the upper surface of the ILM and the ILM itself will not be distinguished in the following text; both will be referred to as the ILM. Related technologies typically determine the optic cup position using the following methods:

[0050] (1) ONH data were acquired in a polar coordinate system with the BMO center as the origin. On each B-scan image, the BMO location and any point on the ILM were connected by a line segment, and the position of the corresponding point on the ILM with the shortest line segment length was taken as the position of the optic cup edge. However, this method does not truly reflect the concept of the total number of optic nerves and has poor accuracy.

[0051] (2) The plane containing the BMO is translated upwards by a fixed distance along the axis to obtain the moved plane. The closed curve where the moved plane intersects the ILM surface is the optic cup edge. If the two do not intersect, it can be considered that there is no optic cup edge. However, the optic cup edge determined in this way is a subjective definition and has no direct relationship with the total amount of optic nerve.

[0052] (3) Based on fundus images or OCT projection images, traditional algorithms or deep learning methods are used to segment the position of the optic cup edge. However, since the optic cup is not the interface between two different physiological structures, there is no clear interface for changes in optical image brightness. Therefore, the results obtained by this method may not be physiologically meaningful. Furthermore, since there is no clear interface on the fundus image or projection image, the repeatability of the results is also relatively poor.

[0053] Therefore, it is necessary to provide a method for determining fundus data with high accuracy. This method will be described in detail below.

[0054] Figure 6 This diagram illustrates the application environment of a fundus data determination method in one embodiment. In an exemplary embodiment, a computer device is provided. The fundus data determination method provided in this application embodiment can be applied to applications such as… Figure 6 The computer device shown may be a server, such as... Figure 6 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining fundus data.

[0055] Those skilled in the art will understand that Figure 6The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0056] This embodiment illustrates the application of this method to a server. It is understood that this method can also be applied to terminals, and to systems that include both terminals and servers, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server can be a standalone server or a server cluster consisting of multiple servers.

[0057] Figure 7 This is a flowchart illustrating a method for determining fundus data in one embodiment. In an exemplary embodiment, such as... Figure 7 As shown, a method for determining fundus data is provided, which can be applied to... Figure 6 The following explanation uses computer equipment as an example, including the following S701 to S704.

[0058] S701, determines the internal limiting membrane and optic disc margin based on first scan data including the optic nerve head.

[0059] In this embodiment, the first scan data may include, but is not limited to, a set of B-scan images or volume data. For example, the first scan data may include a set of B-scan images acquired using a raster scan method within a rectangular region perpendicular to the axial direction of the eye. The first scan data may also include a set of B-scan images acquired using a star-shaped scan method centered on the ONH center. As another example, the first scan data may also include volume data reconstructed from a set of B-scan images.

[0060] Furthermore, the computer device can determine the internal limiting membrane and the optic disc margin based on the first scan data including the optic nerve head. It is understood that the internal limiting membrane is used to characterize its location in three-dimensional space, and the optic disc margin is used to characterize its location in three-dimensional space. Exemplarily, the computer device can input the first scan data into a trained analysis model, and the analysis model can then determine the internal limiting membrane and the optic disc margin.

[0061] In an exemplary embodiment, optionally, S701 above includes: determining the internal limiting membrane and the identifiable layer closest to the optic nerve based on first scan data including the optic nerve head; and determining the optic disc edge based on the closed curve formed by the identifiable layer.

[0062] Optionally, the computer device can perform layered processing on the first scan data to determine identifiable layers and the inner limiting membrane. For example, the computer device can perform layered processing on the first scan data using a preset segmentation algorithm to determine identifiable layers and the inner limiting membrane. The computer device can also perform layered processing on the first scan data using a deep learning model to determine identifiable layers and the inner limiting membrane. The computer device can also respond to user input to determine identifiable layers and the inner limiting membrane by performing layered processing on the first scan data. This embodiment is not limited to these methods.

[0063] It should be noted that physiologically, the Bruce membrane breaks near the optic nerve head, and in this application, the identifiable layer closest to the optic nerve can be understood as the continuous layer containing the Bruce membrane. For example, a computer device can, based on the ocular physiological structure in the first scan data, identify the continuous layer corresponding to the Bruce membrane as the identifiable layer closest to the optic nerve.

[0064] Optionally, the identifiable layer closest to the optic nerve includes at least one of the Bruce membrane, choroid, and sclera. For example, in the first scan data, where the Bruce membrane is present, the identifiable layer is located on the Bruce membrane; where the Bruce membrane is absent but the choroid is present, the identifiable layer is located on the upper surface of the choroid; where the choroid is absent but the sclera is present, the identifiable layer is located on the upper surface of the sclera; and where the sclera is absent (i.e., where the optic nerve head passes through the sclera), the identifiable layer is located at the line connecting the above results. Thus, the determined identifiable layer is a continuous layer, which is beneficial for subsequently accurately determining the optic disc edge and optic cup edge.

[0065] Figure 8 This is a schematic diagram of the layering results in one embodiment. Taking a set of B-scan images acquired at different positions along the axial direction as an example, the first scan data is as follows: Figure 8 As shown, curve 801 at the top of the B-scan image represents the internal limiting membrane, and curve 802 at the bottom of the B-scan image represents the identifiable layer.

[0066] Furthermore, the computer device can determine the optic disc edge based on the closed curve formed by the identifiable layers. In this embodiment, for example, the computer device can determine the closed curve formed by the identifiable layers based on the image corresponding to the identifiable layers and a trained machine learning model, and use the closed curve formed by the identifiable layers as the optic disc edge of the optic nerve head. The computer device can also segment the image based on the grayscale features or structural features corresponding to the identifiable layers to determine the closed curve formed by the identifiable layers, and use the closed curve formed by the identifiable layers as the optic disc edge of the optic nerve head. In some embodiments, the computer device can also perform post-processing such as smoothing on the closed curve formed by the identifiable layers to obtain the optic disc edge.

[0067] In this way, by determining the internal limiting membrane and the identifiable layers closest to the optic nerve based on the first scan data including the optic nerve head, and then determining the optic disc edge more accurately based on the closed curve formed by the identifiable layers.

[0068] S702, based on the surface area formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane, determine the closed curve when the surface area meets the preset conditions as the target curve.

[0069] In this embodiment, the computer device can determine the surface area formed by a closed curve extending from the optic disc edge to the internal limiting membrane. In other words, the optic disc edge and any closed curve on the internal limiting membrane can form a geometric shape, and the lateral surface area of ​​this geometric shape is also the surface area formed from the optic disc edge to the closed curve. Optionally, the computer device can traverse the internal limiting membrane to obtain multiple closed curves on the internal limiting membrane, and for each closed curve, calculate the surface area formed by the closed curve extending from the optic disc edge to the internal limiting membrane.

[0070] Furthermore, the computer device can determine the closed curve that corresponds to the surface area meeting preset conditions as the target curve. In other words, the target curve is a closed curve corresponding to the surface area meeting preset conditions.

[0071] The preset conditions are used to constrain the surface area formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane. Optionally, the preset conditions may include surface areas ranked within a first preset range after being sorted by size; the preset conditions may also include surface areas with the smallest surface area; and the preset conditions may also include surface areas smaller than a preset area threshold. This embodiment does not impose any limitations. Both the first preset range and the preset area threshold can be set according to actual needs.

[0072] S703 determines the optic cup edge of the optic nerve head based on the target curve.

[0073] In this embodiment, after determining the target curve, the computer device can determine the optic cup edge of the optic nerve head based on the target curve. Optionally, the computer device can directly use the target curve as the optic cup edge of the optic nerve head, or it can obtain the optic cup edge of the optic nerve head after post-processing the target curve. Post-processing may include, but is not limited to, at least one of smoothing, enhancement, noise reduction, and filtering.

[0074] Figure 9 This is a schematic diagram of the edge of the viewing disc and the edge of the viewing cup in one embodiment. Continuing with... Figure 8 Taking the B-scan image shown as an example, the edges of the optic disc and optic cup on this B-scan image can be as follows: Figure 9 As shown.

[0075] S704 determines fundus data based on the optic disc margin and optic cup margin.

[0076] In this embodiment, the fundus data is data related to the optic nerve head. Optionally, the fundus data includes, but is not limited to, at least one of the following: disc area, cup area, cup-disc ratio (C / D ratio), neuroretinal rim area (RIM area), cup volume, and average retinal nerve fiber layer thickness. The cup-disc ratio may include, but is not limited to, at least one of the following: average cup-to-disc ratio (Avg C / D ratio), vertical cup-to-disc ratio (Vertical C / D ratio), and horizontal cup-to-disc ratio.

[0077] In the aforementioned method for determining fundus data, the internal limiting membrane and optic disc margin can be determined based on the first scan data including the optic nerve head. Furthermore, based on the surface area formed by the closed curve extending from the optic disc margin to the internal limiting membrane, the closed curve that satisfies preset conditions is identified as the target curve. Therefore, by using the surface area, the surface formed by the closed curve extending from the optic disc margin to the internal limiting membrane can be calculated as a whole. This not only reflects the total number of optic nerves but also results in a highly continuous closed curve. Further, based on the target curve, the optic cup margin of the optic nerve head can be determined relatively accurately, thereby determining fundus data with good accuracy based on the optic disc margin and the optic cup margin.

[0078] In an exemplary embodiment, the above-described fundus data determination method further includes: performing triangular segmentation on the surface formed by the closed curve extending from the edge of the optic disc to the internal limiting membrane to obtain multiple triangles; and determining the surface area based on the sum of the areas of each triangle.

[0079] In this embodiment, optionally, the computer device can use a preset triangulation algorithm to perform triangulation processing on the surface formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane to obtain multiple triangles. The preset triangulation algorithm includes, but is not limited to, the leading edge propagation algorithm or the Delaunay triangulation algorithm.

[0080] Figure 10This is a schematic diagram of a triangle segmentation process in one embodiment, such as... Figure 10 As shown, taking a closed curve 1002 on the optic disc edge 1001 and the inner limiting membrane as an example, after performing triangular segmentation on the surface formed by extending from the optic disc edge 1001 to the closed curve 1002, the surface can be decomposed into multiple sequentially adjacent and non-overlapping triangles. Please continue to refer to... Figure 10 The computer device can divide the surface to obtain triangles with vertices Q1, P1, P2, Q1, Q2, P2, Q2, P2, P3, Q2, Q3, P3, and so on. Among them, P1, P2, P3, etc. are points located on the edge 1001 of the viewing disk, and Q1, Q2, Q3, etc. are points located on the closed curve 1002.

[0081] Therefore, the computer device can determine the surface area based on the sum of the areas of each triangle. Optionally, the computer device can use the sum of the areas of each triangle as the surface area. In some embodiments, the computer device can also obtain the surface area after processing such as correcting the sum of the areas of each triangle; this embodiment is not limited to this.

[0082] Alternatively, the computer device can determine the area of ​​the triangle based on the following equation (1). In equation (1), taking any triangle in three-dimensional space with vertices A, B, and C as an example, , , Representing vectors The components in the x, y, and z directions, respectively. , , Representing vectors The components are located in the x, y, and z directions, respectively. The x, y, and z directions are mutually perpendicular directions in three-dimensional space.

[0083] (1);

[0084] In the above embodiments, since the surface formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane can be divided into multiple triangles, the surface formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane can be decomposed into multiple triangles. In this way, the corresponding surface area can be determined efficiently and accurately based on the sum of the areas of each triangle.

[0085] Figure 11 This is a schematic diagram of a process for determining a target curve in one embodiment. In an exemplary embodiment, such as... Figure 11 As shown, S702 includes S1101 to S1103.

[0086] S1101 transforms the pixels of the inner boundary membrane into candidate points in polar coordinates.

[0087] In this embodiment, the polar coordinate system can be established according to actual needs. Optionally, the polar coordinate system can be determined based on any position within the edge of the viewing disk. Further optionally, the computer device can determine the origin of the polar coordinate system based on the centroid of the edge of the viewing disk, thereby establishing the corresponding polar coordinate system.

[0088] To more clearly illustrate the process of determining the target curve in this application, this section combines... Figure 12 Please provide an explanation. Figure 12 This is a schematic diagram of a polar coordinate system in one embodiment. Taking the centroid of the edge of the viewing disk as the origin of the polar coordinate system as an example, a system can be established as follows: Figure 12 The polar coordinate system shown.

[0089] Then, the computer device converts the pixels of the inner limiting membrane into candidate points in a polar coordinate system. Optionally, the computer device can sample all pixels on the inner limiting membrane according to a first preset sampling rate and convert the sampled pixels into a polar coordinate system to obtain the corresponding candidate points. For example, the computer device performs a polar coordinate transformation on the coordinates of each pixel on the inner limiting membrane in the x and y directions, while keeping the z coordinate unchanged, thus obtaining a surface containing the inner limiting membrane in a polar coordinate system, thereby determining the candidate points in the polar coordinate system. Here, the z direction is the axial direction. Please continue to refer to... Figure 12 In Figure (a), candidate points are as follows: Figure 12 As shown by the black dots in Figure (a), candidate points include, for example, C1, C2, C3, etc.

[0090] S1102 converts the pixels at the edge of the display screen into polar coordinates; each polar coordinate point corresponds to a polar angle.

[0091] In this embodiment, optionally, the computer device can sample all pixels on the edge of the display screen according to a second preset sampling rate, and convert the sampled pixels to a polar coordinate system to obtain the corresponding polar coordinate points. For example, the computer device performs polar coordinate transformation on the coordinates of each pixel on the curve corresponding to the edge of the display screen in the x and y directions, while keeping the z coordinate unchanged, thus obtaining a display screen edge curve in a polar coordinate system, thereby determining the polar coordinate points in the polar coordinate system. Please continue to refer to... Figure 12 In Figure (b), the computer device can convert the pixels on the edge 1201 of the display screen into polar coordinate points P1, P2, P3, etc. in the polar coordinate system.

[0092] It is understandable that each polar coordinate point corresponds to a polar angle. For example, the polar angle... Corresponding polar coordinate point P1, polar angle Corresponding polar coordinate point P2, polar angle The corresponding polar coordinate point P3, and so on.

[0093] S1103, based on the polar coordinate points and the area of ​​the triangles corresponding to the candidate points, and using the shortest path method, determine the closed curve from each candidate point that satisfies the preset conditions as the target curve.

[0094] In this embodiment, please refer to the reference. Figure 10 and Figure 12 After dividing the surface formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane into multiple triangles, each polar angle intersects the edge of the optic disc at a polar coordinate point, for example, adjacent polar angles. and The polar angles intersect the edge of the visual disk at polar coordinate points P1 and P2, respectively. Similarly, each polar angle intersects any closed curve at candidate points, such as adjacent polar angles. and The points intersect the edge of the viewing cup at candidate points Q1 and Q2, respectively. Therefore, the computer device can determine the area of ​​the triangle formed by the polar coordinate points and the corresponding candidate points. For example, the computer device can determine the area of ​​the triangle with points Q1, P1, and P2 in sequence, and the area of ​​the triangle with points Q1, P1, and Q2 in sequence, and so on.

[0095] Furthermore, to determine the closed curve when the surface area satisfies a preset condition—that is, when the sum of the areas of multiple triangles satisfies a preset condition—the computer device can transform the above problem into a graph cutting problem in a polar coordinate system. Based on the polar coordinate points and the areas of the triangles corresponding to the candidate points, and using the shortest path method, the computer device can determine the closed curve from each candidate point whose surface area satisfies the preset condition as the target curve. For example, the computer device can treat each candidate point in the polar coordinate system as all nodes in a graph, and determine a shortest path from left to right from all nodes in the graph based on the shortest path method, where the area of ​​the triangle corresponding to the shortest path satisfies a first preset condition, thereby determining the target curve based on the shortest path.

[0096] In the above embodiments, since the pixels of the inner boundary membrane are transformed into candidate points in polar coordinates, and the pixels of the viewing disk edge are transformed into polar coordinates, and each polar coordinate point corresponds to a polar angle, the closed curve that satisfies the preset conditions can be determined from each candidate point based on the area of ​​the triangle corresponding to the polar coordinate point and the candidate point, thus transforming the problem of determining the surface area that satisfies the preset conditions into the problem of determining the shortest path in polar coordinates, thereby improving the efficiency of determining the target curve.

[0097] Figure 13 This is a schematic diagram of another process for determining a target curve in one embodiment. In an exemplary embodiment, such as... Figure 13 As shown, S1103 includes S1301 to S1304.

[0098] S1301, Based on the area of ​​the first triangle, determine the first loss value corresponding to any candidate point.

[0099] In this embodiment, the computer device can determine a first loss value corresponding to each candidate point. The first loss value can be determined based on the area of ​​a first triangle. The first triangle is determined based on the candidate point, a first polar coordinate point, and a second polar coordinate point.

[0100] Optionally, the computer device can determine the area of ​​the first triangle based on the candidate point, the first polar coordinate point, and the second polar coordinate point, and use the area of ​​the first triangle as the first loss value for the corresponding candidate point. In some embodiments, the computer device can also obtain the corresponding first loss value by performing weighted processing on the area of ​​the first triangle.

[0101] Among them, the first polar coordinate point is the polar coordinate point that corresponds to the same polar angle as the candidate point; the first polar coordinate point and the second polar coordinate point are the polar coordinate points that correspond to two adjacent polar angles along the polar axis direction.

[0102] For example, taking candidate point C1 as an example, candidate point C1 and polar coordinate point P1 correspond to the same polar angle. And the polar angles of polar coordinate points P1 and P2 that are adjacent along the polar axis are... and Therefore, in this case, the first polar coordinate point is polar coordinate point P1, and the second polar coordinate point is polar coordinate point P2. Furthermore, the computer device determines the area of ​​the first triangle whose vertices are candidate point C1, polar coordinate point P1, and polar coordinate point P2 in sequence. and the area The first loss value is used as the candidate point C1. The other first loss values ​​are similar and will not be elaborated here.

[0103] S1302, Based on the area of ​​the second triangle, determine the second loss value corresponding to the line connecting the first candidate point and the second candidate point.

[0104] In this embodiment, the first candidate point and the second candidate point are two different candidate points, and the first candidate point and the second candidate point correspond to two adjacent polar angles along the polar axis direction. For example, please refer to... Figure 12 In Figure (a), if the first candidate point is candidate point C1 to candidate point C5, the second candidate point can be candidate point C6 to candidate point C10.

[0105] Furthermore, the computer device can determine the second loss value corresponding to the line connecting the first candidate point and the second candidate point. The second loss value can be determined based on the area of ​​the second triangle. The second triangle is determined based on the first candidate point, the second candidate point, and the third polar coordinate point.

[0106] Similarly, the computer device can determine the area of ​​the second triangle based on the first candidate point, the second candidate point, and the third polar coordinate point, and use the area of ​​the second triangle as the second loss value corresponding to the line connecting the first candidate point and the second candidate point. In some embodiments, the computer device can also obtain the corresponding second loss value after weighting or other processing of the area of ​​the second triangle.

[0107] The third polar coordinate point is the polar coordinate point that shares the same polar angle as the second candidate point. In some embodiments, the third polar coordinate point is also the aforementioned second polar coordinate point. For example, taking candidate point C1 as the first candidate point and candidate point C6 as the second candidate point, candidate points C1 and C6 respectively correspond to two adjacent polar angles along the polar axis direction. and Both polar coordinate point P2 and candidate point C6 correspond to polar angles. Therefore, in this case, the third polar coordinate point is polar coordinate point P2, and the computer device determines the area of ​​the second triangle whose vertices are candidate points C1, C6, and polar coordinate point P2 in sequence. and the area The second loss value is used as the line connecting candidate point C1 and candidate point C6. Other second loss values ​​are similar and will not be elaborated here.

[0108] S1303, determine the shortest path based on the first loss value and the second loss value.

[0109] In this embodiment, according to S1301 and S1302, the computer device can determine a first loss value corresponding to any candidate point and a second loss value for the line connecting any first candidate point and a second candidate point. Then, the computer device can determine the shortest path based on the first and second loss values.

[0110] Optionally, the computer device can select one candidate point from the candidate points corresponding to each polar coordinate point as a candidate point, and determine a candidate path based on all candidate points and the lines connecting adjacent candidate points. This process can be repeated to determine multiple candidate paths. Here, a candidate point corresponding to a polar coordinate point refers to a candidate point that shares the same polar angle as that polar coordinate point.

[0111] For example, please continue to refer to Figure 12 Figure (a) and Figure 12In Figure (b), for polar coordinate point P1, the candidate points corresponding to P1 include candidate points C1 to C5; for polar coordinate point P2, the candidate points corresponding to P2 include candidate points C6 to C10; and so on for other polar coordinate points. Assuming that candidate point C1 is selected as a candidate point from candidate points C1 to C5, and candidate point C7 is selected as a candidate point from candidate points C6 to C10, and so on, each polar coordinate point can determine a corresponding candidate point. Please refer to [further details]. Figure 12 In Figure (c), the lines connecting these candidate points form a candidate path 1202.

[0112] Furthermore, the computer device can determine the sum of the first and second loss values ​​corresponding to each candidate path. This sum is equal to the sum of the first loss values ​​of all candidate points within the candidate path and the second loss values ​​of the lines connecting adjacent candidate points. It can be understood that the sum of the first and second loss values ​​corresponding to each candidate path is equal to the surface area formed by extending from the edge of the display disc to that candidate path.

[0113] Furthermore, the computer device can traverse all candidate paths and, based on the sum of the first and second loss values ​​corresponding to each candidate path, select the candidate path with the smallest sum of the first and second loss values ​​as the shortest path. Thus, the shortest path includes the target point corresponding to each polar coordinate point among the candidate points and the lines connecting all target points, and the shortest path corresponds to the shortest path with the smallest sum of the first and second loss values.

[0114] S1304, determine the target curve based on the shortest path.

[0115] In this embodiment, the computer device can convert the target points on the shortest path to the Cartesian coordinate system to obtain the corresponding target curve. Alternatively, the computer device can perform post-processing such as smoothing on the target points on the shortest path before converting them to the Cartesian coordinate system to obtain the corresponding target curve. This embodiment is not limited to these methods.

[0116] In the above embodiments, since the first triangle is determined based on candidate points, a first polar coordinate point, and a second polar coordinate point, and the first polar coordinate point corresponds to the same polar angle as the candidate point, and the first and second polar coordinate points are polar coordinate points corresponding to two adjacent polar angles along the polar axis, the first loss value corresponding to any candidate point can be determined based on the area of ​​the first triangle. Since the second triangle is determined based on a first candidate point, a second candidate point, and a third polar coordinate point; the first and second candidate points are two different candidate points, and the first and second candidate points correspond to two adjacent polar angles along the polar axis, and the third polar coordinate point is a polar coordinate point corresponding to the same polar angle as the second candidate point, the second loss value corresponding to the line connecting the first and second candidate points can be determined based on the area of ​​the second triangle. Furthermore, since the shortest path includes the target point corresponding to each polar coordinate point among the candidate points and the line connecting each target point, the sum of the first and second loss values ​​corresponding to the shortest path is the smallest. Therefore, based on the first and second loss values, the shortest path can be efficiently determined, thereby determining the target curve whose surface area meets the preset conditions based on the shortest path.

[0117] In one exemplary embodiment, optionally, the radial distance between the first candidate point and the second candidate point satisfies a second preset condition.

[0118] In this embodiment, to constrain the smoothness of the obtained shortest path, the computer device constrains the radial distance between the first candidate point and the second candidate point to meet a second preset condition. The second preset condition can be set according to requirements; for example, the radial distance between the first candidate point and the second candidate point is less than a preset threshold, or the radial distance between the first candidate point and the second candidate point is within a preset range. For example, the polar coordinates of the first candidate point are denoted as (…). , Let the polar coordinates of the second candidate point be (). , ),but dR is a preset value, and i and j are two adjacent positive integers.

[0119] In the above embodiments, by constraining the radial distance between the first candidate point and the second candidate point to meet the second preset condition, the situation of excessive jumps between target points in the shortest path can be reduced, and the smoothness of the determined shortest path can be improved.

[0120] Figure 14 This is a schematic diagram of the process for determining the edge of the viewing disc in one embodiment. In an exemplary embodiment, such as... Figure 14 As shown, the above-mentioned "determining the optic disc edge based on the closed curve formed by the identifiable layer" includes S1401 to S1404.

[0121] S1401, the first scan data is filtered based on the identifiable layer to obtain the second scan data within the first preset range where the identifiable layer is located.

[0122] In this embodiment, the first preset range is a range that uses identifiable layers as a reference, and it can be set according to requirements. For example, the first preset range may include the range between a first sub-range and a second sub-range.

[0123] Optionally, to exclude the influence of data above the Bruce membrane, the first preset range may include a preset distance from the identifiable layer to below the identifiable layer. For example, the computer device selects the identifiable layer and a second scan data 100 micrometers below the identifiable layer from the first scan data. This eliminates the influence of data above the Bruce membrane, ensuring that the maximum contrast of the obtained image occurs at the junction of the choroid / sclera and optic nerve, reducing interference from the contrast at the retinal margins. This also provides accurate results for eyes with paradiscal atrophy, improving the accuracy and stability of the obtained first curve.

[0124] S1402, Axial projection is performed on the second scan data to obtain a two-dimensional projected image.

[0125] In this embodiment, axial projection refers to projection along the axial direction, that is, the optical axis direction. Optionally, the computer device can use a preset projection algorithm to perform axial projection on the second scan data to obtain a two-dimensional projected image. The preset projection algorithm includes, but is not limited to, at least one of the following: Maximum Intensity Projection (MIP) algorithm, Average Intensity Projection (AIP) algorithm, or weighted projection algorithm.

[0126] S1403, Segmentation is performed based on the two-dimensional projection image to determine the first curve corresponding to the edge of the viewing disk in the two-dimensional projection image.

[0127] In this embodiment, optionally, the computer device can use a preset segmentation algorithm to segment the two-dimensional projection image and determine the first curve corresponding to the edge of the optic disc in the two-dimensional projection image. The preset segmentation algorithm includes, but is not limited to, at least one of a threshold segmentation algorithm or a morphological segmentation algorithm. It is understood that the first curve is the curve corresponding to the edge of the optic disc on the xy-plane.

[0128] S1404, Project the first curve along the axis to the identifiable layer to determine the optic disc edge of the optic nerve head.

[0129] In this embodiment, for example, the computer device can project the first curve along the axial direction to obtain the projection result, and determine the position of the disc edge in the axial direction based on the intersection position of the projection result and the identifiable layer, so as to determine the three-dimensional disc edge.

[0130] In the above embodiments, since the first scan data can be filtered based on identifiable layers, second scan data within a first preset range of identifiable layers that meet actual needs can be obtained. Furthermore, since the second scan data can be axially projected to obtain a two-dimensional projection image, segmentation based on the two-dimensional projection image can efficiently determine the first curve corresponding to the optic disc edge in the two-dimensional projection image. Thus, after projecting the first curve axially onto the identifiable layers, a relatively accurate determination of the optic disc edge of the optic nerve head can be achieved.

[0131] In an exemplary embodiment, optionally, S1403 above includes: inputting a two-dimensional projection image into a first machine learning model to determine a first classification result for each pixel in the two-dimensional projection image; performing a first post-processing on the first classification result for each pixel in the two-dimensional projection image to obtain a first curve.

[0132] In this embodiment, the first machine learning model includes a supervised learning model, a semi-supervised learning model, or an unsupervised learning model. Exemplarily, the machine learning model may include, but is not limited to, at least one of the following: Convolutional Neural Networks (CNN) models, Recurrent Neural Networks (RNN) models, Fully Convolutional Neural Networks (FCN) models, Radial Basis Function (RBF) models, Deep Belief Networks (DBN) models, Elman models, or combinations thereof. In some embodiments, the first machine learning model includes a deep learning model based on the Unet architecture.

[0133] Optionally, the first machine learning model is trained based on multiple two-dimensional projected image samples and a first classification label corresponding to each two-dimensional projected image sample. The first classification label is used to indicate whether each pixel in the two-dimensional projected image sample belongs to the optic disc region. In this way, the first machine learning module has the ability to determine whether each pixel in the two-dimensional projected image belongs to the optic disc region.

[0134] Then, the computer device inputs the two-dimensional projected image into the first machine learning model, which can then determine the first classification result for each pixel in the two-dimensional projected image. The first classification result characterizes whether the corresponding pixel belongs to the optic disc region. For example, after inputting the two-dimensional projected image into the first machine learning model, the computer device can obtain a binary classification image of the two-dimensional projected image. One class of pixels in the binary classification image represents pixels belonging to the interior of the optic disc region, and the other class represents pixels belonging to the exterior of the optic disc region.

[0135] Furthermore, the computer device performs a first post-processing on the first classification result of each pixel in the two-dimensional projected image to obtain the first curve. Optionally, the first post-processing includes, but is not limited to, at least one of connected component extraction, smoothing, enhancement, noise reduction, and filtering. Further, the computer device may first perform connected component analysis based on the first classification result of each pixel in the two-dimensional projected image to obtain a target connected component, and then obtain the first curve based on the closed curve on the outer envelope of the target connected component.

[0136] For example, a computer device can extract the maximum connected component from the first classification result of each pixel in a two-dimensional projected image, and use the closed curve of the outer envelope of the maximum connected component as the first curve. In some embodiments, the computer device can also smooth the closed curve of the outer envelope of the maximum connected component to obtain the first curve.

[0137] In the above embodiments, since the two-dimensional projection image can be input into the first machine learning model to determine the first classification result of each pixel in the two-dimensional projection image, and the first classification result is used to characterize whether the corresponding pixel belongs to the optic disc region, the first post-processing of the first classification result of each pixel in the two-dimensional projection image can efficiently and accurately obtain the first curve corresponding to the edge of the optic disc through machine learning.

[0138] In one exemplary embodiment, optionally, any one of the following S1402 above:

[0139] (1) The second scan data is averaged and projected to obtain a two-dimensional projection image.

[0140] For example, a computer device can determine the average value of all pixel values ​​in the axial direction of the second scan data to obtain the corresponding two-dimensional projected image.

[0141] (2) The second scan data is denoised to obtain the third scan data, and the third scan data is projected to the maximum value to obtain a two-dimensional projection image.

[0142] Optionally, the computer device can perform noise reduction processing on the second scan data along the axial direction using a preset noise reduction algorithm. Further optionally, the computer device can perform noise reduction processing on all the second scan data along the axial direction to obtain the third scan data, or it can perform noise reduction processing on a portion of the second scan data along the axial direction to obtain the third scan data. The preset noise reduction algorithm includes, but is not limited to, low-pass noise reduction algorithms, filtering noise reduction algorithms, transform domain noise reduction algorithms, or deep learning noise reduction algorithms. This embodiment is not limited to any of these. It is understood that the third scan data is still a 3D volumetric data. For example, the computer device can perform low-pass noise reduction along the axial direction of the second scan data, and the size of the low-pass window can be set as needed, for example, to 30 micrometers.

[0143] Furthermore, the computer device projects the third scan data to obtain a two-dimensional projected image by performing a maximum value projection. For example, the computer device can determine the maximum value of all pixel values ​​along the axial direction of the second scan data to obtain the corresponding two-dimensional projected image.

[0144] In the above embodiments, the signal-to-noise ratio of the obtained two-dimensional projected image can be improved by mean projection. The signal-to-noise ratio of the two-dimensional projected image and the ability to identify the choroid / sclera layer can also be improved by denoising the second scan data to obtain the third scan data and then projecting the third scan data to obtain the maximum value.

[0145] Figure 15 This is a schematic diagram of a two-dimensional projection image and a first curve in one embodiment, such as... Figure 15 As shown, Figure 15 Figure (a) in the figure shows a two-dimensional projection diagram. Figure 15 Figure (b) shows a first classification result, where areas belonging to the optic disc are displayed in white, and areas not belonging to the optic disc are displayed in black. Figure 15 Figure (c) shows the first curve obtained based on the two-dimensional projection image.

[0146] In an exemplary embodiment, optionally, the above-mentioned "determining the internal limiting membrane and the identifiable layer closest to the optic nerve based on the first scan data including the optic nerve head" includes: determining the fundus scan image corresponding to the first scan data; inputting the fundus scan image into a second machine learning model to determine the second classification result of each pixel in the fundus scan image; performing a second post-processing on the second classification result of each pixel in the fundus scan image to determine the identifiable layer and the internal limiting membrane.

[0147] In this embodiment, optionally, the computer device can acquire fundus scan images sent by other devices, or it can acquire fundus scan images from a preset storage space; this embodiment is not limited to this. The fundus scan images include, but are not limited to, B-scan images. For example, the computer device can acquire OCT data of the posterior segment of the eye containing the ONH location, and perform image reconstruction based on the OCT data, using the resulting B-scan image as the fundus scan image. In some embodiments, the computer device can also reconstruct volume data from a set of B-scan images and perform layered processing based on the volume data.

[0148] The second machine learning model includes supervised learning models, semi-supervised learning models, or unsupervised learning models. Exemplarily, the machine learning model may include, but is not limited to, at least one of the following: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Fully Convolutional Neural Networks (FCN), Generative Adversarial Networks (GAN), Back-propagation (BP) machine learning models, Radial Basis Functions (RBF) models, Deep Belief Networks (DBN) models, Elman models, or combinations thereof. In some embodiments, the second machine learning model includes a deep learning model based on the Unet architecture.

[0149] Optionally, the second machine learning model is trained based on multiple fundus scan image samples and a corresponding second classification label for each fundus scan image sample. The second classification label is used to indicate the ocular physiological structure to which each pixel in the fundus scan image sample belongs, such as marking that the pixel belongs to the choroid, sclera, retinal pigment epithelium (RPE) layer, etc. In this way, the first machine learning module has the ability to determine the ocular physiological structure to which each pixel in the fundus scan image belongs based on the fundus scan image.

[0150] Furthermore, the computer device inputs the fundus scan image into a second machine learning model, which can then determine the second classification result for each pixel in the fundus scan image. This second classification result is used to characterize the corresponding ocular physiological structure to which the pixel belongs.

[0151] Furthermore, by performing a second post-processing on the second classification results of each pixel in the fundus scan image, the computer device can determine the identifiable layers and the internal limiting membrane. Optionally, the second post-processing includes, but is not limited to, at least one of screening, smoothing, enhancement, or filtering. Further optionally, the computer device can analyze the second classification results of each pixel in the fundus scan image to obtain the identifiable layers and the internal limiting membrane. For example, the computer device analyzes the second classification results to determine a first interface between the choroid and the retinal layer above the choroid, and determines the identifiable layers based on the first interface; and determines a second interface between the vitreous body and the optic nerve layer, and determines the internal limiting membrane based on the second interface.

[0152] In some embodiments, during the determination of identifiable layers, at the location of paradiscal atrophy, if there is no choroidal atrophy, the identifiable layer is located at the junction of the choroid and the superior tissue; if there is choroidal atrophy, at the location of choroidal atrophy, the identifiable layer is located at the junction of the sclera and the superior tissue.

[0153] In the above embodiments, since the fundus scan image corresponding to the first scan data can be determined, the fundus scan image is input into the second machine learning model to determine the second classification result of each pixel in the fundus scan image. Furthermore, the second classification result is used to characterize the ocular physiological structure to which the corresponding pixel belongs. Therefore, after performing the second post-processing on the second classification result of each pixel in the fundus scan image, the identifiable layer and internal limiting membrane can be determined efficiently and accurately through machine learning.

[0154] In one exemplary embodiment, optionally, the fundus data includes the optic cup volume. S704 described above includes: performing planar fitting on the optic cup edge to determine a fitting plane; determining an enclosed space based on the fitting plane, the internal limiting membrane, and the optic cup edge; and determining the optic cup volume of the optic nerve head based on the volume of the enclosed space.

[0155] In this embodiment, after obtaining the optic cup edge, the computer device can determine the optic cup volume based on the volume of the region enclosed by the optic cup edge on the ILM surface. Specifically, the computer device performs planar fitting on the optic cup edge to obtain a corresponding fitting plane. Then, the computer device can use this fitting plane and the ILM surface corresponding to the inner limiting membrane as the upper and lower boundaries of the enclosed space, and the torus formed by the closed curve of the optic cup edge extending axially in the xy plane as the lateral boundary of the enclosed space. Here, the x and y directions are two directions perpendicular to the axial direction, i.e., the z direction.

[0156] Furthermore, the computer device can use the volume of the enclosed space as the optic cup volume of the optic nerve head. In some embodiments, the computer device can also further process the volume of the enclosed space to obtain the optic cup volume of the optic nerve head.

[0157] In the above embodiments, since the optic cup edge can be fitted with a plane to determine the fitting plane, and the enclosed space can be determined based on the fitting plane, the inner limiting membrane, and the optic cup edge, the volume of the optic cup of the optic nerve head can be determined relatively accurately based on the volume of the enclosed space.

[0158] In some embodiments, the computer device may optionally store fundus data; however, this embodiment does not limit the storage method of the computer device.

[0159] In some embodiments, the computer device may optionally display fundus data; however, this embodiment does not limit the display method of the computer device.

[0160] Figure 16 This is a schematic diagram shown in one embodiment, such as... Figure 16 As shown, the computer device can display the positions of the edges of the viewing disc and the viewing cup on the projected image. In one embodiment, the transparency of the projected image can also be adjusted.

[0161] Furthermore, computer devices can display fundus data. For example, such as... Figure 16 As shown, the computer device can display the average cup-to-disc ratio, average retinal nerve fiber layer thickness, optic cup area, optic cup volume, rim area, vertical cup-to-disc ratio, and horizontal cup-to-disc ratio. Here, mm represents millimeters, and μm represents micrometers.

[0162] To more clearly illustrate the fundus data determination method of this application, this paper combines... Figure 17 Please provide an explanation. Figure 17 This is a schematic diagram of a method for determining fundus data in one embodiment, as shown below. Figure 17 As shown, computer equipment can execute this fundus data determination method according to the following procedure.

[0163] S1701, Determine the fundus scan image corresponding to the first scan data.

[0164] S1702, Input the fundus scan image into the second machine learning model to determine the second classification result of each pixel in the fundus scan image.

[0165] S1703, perform a second post-processing on the second classification results of each pixel in the fundus scan image to determine the identifiable layer and internal limiting membrane.

[0166] S1704, the first scan data is filtered based on the identifiable layer to obtain the second scan data within the first preset range where the identifiable layer is located.

[0167] S1705, axial projection is performed on the second scan data to obtain a two-dimensional projected image. This can be achieved by mean projection of the second scan data to obtain the two-dimensional projected image, or by noise reduction of the second scan data to obtain third scan data, and then maximum value projection of the third scan data to obtain the two-dimensional projected image.

[0168] S1706, Input the two-dimensional projected image into the first machine learning model to determine the first classification result of each pixel in the two-dimensional projected image.

[0169] S1707, perform first post-processing on the first classification result of each pixel in the two-dimensional projection image to obtain the first curve corresponding to the edge of the viewing disk.

[0170] S1708, the first curve is projected axially onto the identifiable layer to determine the edge of the optic disc of the optic nerve head.

[0171] S1709 transforms the pixels of the inner boundary membrane into candidate points in polar coordinates.

[0172] S1710 converts the pixels at the edge of the display screen into polar coordinates.

[0173] S1711, Based on the area of ​​the first triangle, determine the first loss value corresponding to any candidate point.

[0174] S1712, Based on the area of ​​the second triangle, determine the second loss value corresponding to the line connecting the first candidate point and the second candidate point.

[0175] S1713, determine the shortest path based on the first loss value and the second loss value.

[0176] S1714, determine the target curve based on the shortest path.

[0177] S1715, determine the optic cup edge of the optic nerve head based on the target curve.

[0178] S1716, determining fundus data based on the optic disc margin and optic cup margin.

[0179] The processes S1701 to S1716 can be referred to in the above embodiments, and will not be repeated here.

[0180] Figure 18The diagram shows a comparison of the effects of related technologies and this application. It is assumed that the continuity of the surface area formed by the closed curve extending from the edge of the optic disc to the internal limiting membrane is not considered. Instead, a plane with the minimum area is solved independently in each small part of the meridional angle in polar coordinates, and then the sum of all minimum areas is calculated. The surface obtained in this way is likely to be fragmented in 3D space, and the area of ​​such fragmented surface cannot best represent the total area of ​​the optic nerve.

[0181] Furthermore, when calculating the optic cup volume, if the original optic cup edge position is used, the physiological meaning of the calculated optic cup volume becomes unclear because the original optic cup edge position does not have spatial continuity.

[0182] like Figure 18 As shown, Figure 18 Figure (a) shows the optic disc edge and optic cup edge without considering the continuity of the surface area formed by the closed curve extending from the optic disc edge to the inner limiting membrane. Figure 18 Figure (b) shows the optic disc edge and optic cup edge obtained in this application. The outer closed curves represent the optic disc position, and the inner closed curves represent the optic cup position. It can be seen that, without considering the continuity of surface area, the obtained optic cup position has an abrupt change on the left side of the ONH, and its physiological significance is unclear. In contrast, the optic cup position of this application is more continuous and smooth.

[0183] As can be seen, since this application minimizes the area of ​​a continuous surface, it can most realistically reflect the total amount of all optic nerves, and the result obtained is a closed loop with high continuity, which makes the subsequent calculation of the optic cup volume more stable and physiologically meaningful, and the accuracy and repeatability of quantitative indicators such as the C / D ratio of ONH are higher.

[0184] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0185] Based on the same inventive concept, this application also provides a fundus data determination device for implementing the fundus data determination method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more fundus data determination device embodiments provided below can be found in the limitations of the fundus data determination method described above, and will not be repeated here.

[0186] Figure 19 This is a structural block diagram of a fundus data determination device in one embodiment. In an exemplary embodiment, such as... Figure 19 As shown, a fundus data determination device 1900 is provided, comprising: a first determination module 1901, a second determination module 1902, a third determination module 1903, and a fourth determination module 1904, wherein:

[0187] The first determining module 1901 is used to determine the internal limiting membrane and the edge of the optic disc based on the first scan data including the optic nerve head.

[0188] The second determining module 1902 is used to determine the target curve when the surface area meets the preset conditions based on the surface area formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane.

[0189] The third determining module 1903 is used to determine the edge of the optic cup of the optic nerve head based on the target curve.

[0190] The fourth determination module 1904 is used to determine fundus data based on the edge of the optic disc and the edge of the optic cup.

[0191] The modules in the aforementioned fundus data determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0192] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0193] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0194] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0195] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0196] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0197] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining fundus data, characterized in that, The method includes: The internal limiting membrane and optic disc margins were determined based on the first scan data including the optic nerve head. Based on the surface area formed by the closed curve extending from the edge of the visual disk to the inner boundary membrane, the closed curve that satisfies the preset conditions is determined as the target curve; The optic cup edge of the optic nerve head is determined based on the target curve; The fundus data are determined based on the edge of the optic disc and the edge of the optic cup; The determination of the target curve based on the surface area formed by the closed curve extending from the edge of the optic disc to the inner limiting membrane, where the surface area satisfies a preset condition, includes: The pixels of the inner boundary membrane are transformed into candidate points in polar coordinates. The pixels at the edge of the display screen are converted into polar coordinates in the polar coordinate system; each polar coordinate point corresponds to a polar angle. Based on the area of ​​the triangles corresponding to the polar coordinate points and the candidate points, and using the shortest path method, a closed curve whose surface area satisfies the preset condition is determined from each of the candidate points as the target curve; wherein, the triangle is obtained by dividing the surface formed by the closed curve extending from the edge of the optic disc to the inner boundary membrane into triangles, and the surface area is determined based on the sum of the areas of each triangle.

2. The method according to claim 1, characterized in that, The determination of the internal limiting membrane and optic disc margin based on first scan data including the optic nerve head includes: Based on the first scan data including the optic nerve head, the internal limiting membrane and the identifiable layers closest to the optic nerve are determined; The edge of the visual disc is determined based on the closed curve formed by the recognizable layers.

3. The method according to claim 2, characterized in that, The identifiable layer closest to the optic nerve includes at least one of the Bruce membrane, choroid, and sclera.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the target curve from among the candidate points whose surface area satisfies the preset condition based on the area of ​​the triangles corresponding to the polar coordinate points and the candidate points, using the shortest path method, includes: Based on the area of ​​the first triangle, a first loss value is determined for any candidate point; the first triangle is determined based on the candidate point, a first polar coordinate point, and a second polar coordinate point, wherein the first polar coordinate point is a polar coordinate point corresponding to the same polar angle as the candidate point; the first polar coordinate point and the second polar coordinate point are polar coordinate points corresponding to two adjacent polar angles along the polar axis direction; Based on the area of ​​the second triangle, the second loss value corresponding to the line connecting the first candidate point and the second candidate point is determined; the second triangle is determined based on the first candidate point, the second candidate point, and the third polar coordinate point; the first candidate point and the second candidate point are two different candidate points, and the first candidate point and the second candidate point correspond to two adjacent polar angles along the polar axis direction, and the third polar coordinate point is a polar coordinate point that corresponds to the same polar angle as the second candidate point; The shortest path is determined based on the first loss value and the second loss value; the shortest path includes the target point corresponding to each polar coordinate point among the candidate points and the line connecting each target point, and the sum of the first loss value and the second loss value corresponding to the shortest path is the smallest; The target curve is determined based on the shortest path.

5. The method according to claim 4, characterized in that, The radial distance between the first candidate point and the second candidate point satisfies the second preset condition.

6. The method according to claim 2 or 3, characterized in that, Determining the optic disc edge based on the closed curve formed by the identifiable layers includes: Based on the identifiable layer, the first scan data is filtered to obtain the second scan data within the first preset range where the identifiable layer is located; A two-dimensional projected image is obtained by axially projecting the second scan data; Segmentation is performed based on the two-dimensional projection image to determine the first curve corresponding to the edge of the visual disk in the two-dimensional projection image; The first curve is projected axially onto the identifiable layer to determine the optic disc edge of the optic nerve head.

7. The method according to claim 6, characterized in that, The step of segmenting based on the two-dimensional projection image to determine the first curve corresponding to the edge of the optic disc in the two-dimensional projection image includes: The two-dimensional projected image is input into a first machine learning model to determine the first classification result of each pixel in the two-dimensional projected image; the first classification result is used to characterize whether the corresponding pixel belongs to the visual disc region. The first classification result of each pixel in the two-dimensional projection image is subjected to a first post-processing to obtain the first curve.

8. The method according to claim 6, characterized in that, The axial projection of the second scan data to obtain a two-dimensional projected image includes at least one of the following: The two-dimensional projected image is obtained by mean projection of the second scan data; The second scan data is denoised to obtain the third scan data, and the third scan data is projected to the maximum value to obtain the two-dimensional projected image.

9. The method according to any one of claims 1-3, characterized in that, The fundus data includes the optic cup volume; determining the fundus data based on the optic disc edge and the optic cup edge includes: Perform plane fitting on the edge of the viewing cup to determine the fitting plane; The enclosed space is determined based on the fitted plane, the inner limiting membrane, and the edge of the viewing cup; The optic cup volume of the optic nerve head is determined based on the volume of the enclosed space.

10. The method according to claim 2 or 3, characterized in that, The determination of the internal limiting membrane and the identifiable layers closest to the optic nerve based on first scan data including the optic nerve head includes: Determine the fundus scan image corresponding to the first scan data; The fundus scan image is input into a second machine learning model to determine the second classification result of each pixel in the fundus scan image; A second post-processing is performed on the second classification results of each pixel in the fundus scan image to determine the identifiable layer and the internal limiting membrane.

Images